# Synthèse vocale en anglais, Artificial Analysis, édition du 9 novembre 2026

Tableau repris tel que Artificial Analysis le publie : préférences de votants à l'aveugle entre deux voix qui lisent le même texte, chaque modèle avec ses propres voix (arène Provider Voice, anglais américain et britannique). Aucun score de QUELLE IA, aucun score combiné. Édition du 9 novembre 2026.

| Rang | Modèle | Éditeur | Valeur (Elo) |
| ---: | --- | --- | --- |
| 1 | [Eleven v4](https://quelleia.com/voix/modeles/eleven-v4/) | ElevenLabs | 1 339 |
| 2 | [Eleven v4 Turbo](https://quelleia.com/voix/modeles/eleven-v4-turbo/) | ElevenLabs | 1 335 |
| 3 | [Qwen-Audio-3.1-TTS-Plus](https://quelleia.com/voix/modeles/alibaba-qwen-audio-3-1-tts-plus/) | Alibaba | 1 303 |
| 4 | [Sonic 3.6](https://quelleia.com/voix/modeles/cartesia-sonic-3-6/) | Cartesia | 1 297 |
| 5 | [Simba 3.5](https://quelleia.com/voix/modeles/speechifyai-simba-3-5/) | SpeechifyAI | 1 286 |
| 6 | [Gemini 3.8 Flash TTS](https://quelleia.com/voix/modeles/google-gemini-3-8-flash-tts/) | Google | 1 283 |
| 7 | [Fish Audio Drama 3](https://quelleia.com/voix/modeles/fish-audio-drama-3/) | Fish Audio | 1 275 |
| 8 | [Lightning V3.1 Pro (Oct 2026)](https://quelleia.com/voix/modeles/smallest-ai-lightning-v3-1-pro-oct-2026/) | Smallest AI | 1 273 |
| 9 | [Qwen-Audio-3.0-TTS-Plus](https://quelleia.com/voix/modeles/alibaba-qwen-audio-3-0-tts-plus/) | Alibaba | 1 268 |
| 9 | [Realtime TTS-2](https://quelleia.com/voix/modeles/inworld-realtime-tts-2/) | Inworld AI | 1 268 |
| 11 | [Gemini 3.8 Flash-Lite TTS](https://quelleia.com/voix/modeles/google-gemini-3-8-flash-lite-tts/) | Google | 1 260 |
| 12 | [Simba 3.2](https://quelleia.com/voix/modeles/speechifyai-simba-3-2/) | SpeechifyAI | 1 250 |
| 13 | [Fish Audio Drama 3 Preview](https://quelleia.com/voix/modeles/fish-audio-drama-3-preview/) | Fish Audio | 1 241 |
| 14 | [Breeze TTS 2](https://quelleia.com/voix/modeles/breeze-tts-2/) | BreezeBlue | 1 228 |
| 15 | [AssemblyAI-TTS-1](https://quelleia.com/voix/modeles/assemblyai-tts-1/) | AssemblyAI | 1 224 |
| 16 | [Realtime TTS-2 Flash](https://quelleia.com/voix/modeles/inworld-realtime-tts-2-flash/) | Inworld AI | 1 217 |
| 16 | [Voxtral 3 TTS](https://quelleia.com/voix/modeles/mistral-ai-voxtral-3-tts/) | Mistral AI | 1 217 |
| 18 | [StepAudio 2.5 TTS (Aug 2026)](https://quelleia.com/voix/modeles/stepaudio-2-5-tts-aug-2026/) | StepFun | 1 216 |
| 18 | [v3 Conversational](https://quelleia.com/voix/modeles/elevenlabs-v3-conversational/) | ElevenLabs | 1 216 |
| 20 | [Gemini 3.1 Flash TTS](https://quelleia.com/voix/modeles/google-gemini-3-1-flash-tts/) | Google | 1 215 |
| 21 | [Luna TTS](https://quelleia.com/voix/modeles/vui-labs-luna-tts/) | VUI Labs | 1 204 |
| 22 | [Sonic 3.5](https://quelleia.com/voix/modeles/cartesia-sonic-3-5/) | Cartesia | 1 196 |
| 23 | [Eleven v3](https://quelleia.com/voix/modeles/elevenlabs-eleven-v3/) | ElevenLabs | 1 189 |
| 24 | [Fish Audio S2.1 Pro (Oct 2026)](https://quelleia.com/voix/modeles/fish-audio-s2-1-pro-oct-2026/) | Fish Audio | 1 188 |
| 25 | [Ming-3.0-tts](https://quelleia.com/voix/modeles/ant-group-ming-3-0-tts/) | Ant Group | 1 187 |
| 26 | [Soniox TTS Real-Time v2](https://quelleia.com/voix/modeles/soniox-tts-real-time-v2/) | Soniox | 1 181 |
| 27 | [Gradium TTS (Sep 2026)](https://quelleia.com/voix/modeles/gradium-tts-sep-2026/) | Gradium | 1 176 |
| 28 | [MiniMax Speech 2.8 HD](https://quelleia.com/voix/modeles/minimax-speech-2-8-hd/) | MiniMax | 1 175 |
| 29 | [Gradium TTS (Oct 2026)](https://quelleia.com/voix/modeles/gradium-tts-oct-2026/) | Gradium | 1 168 |
| 30 | [SpaceXAI TTS](https://quelleia.com/voix/modeles/spacexai-tts/) | SpaceXSI | 1 159 |
| 31 | [Falcon 2](https://quelleia.com/voix/modeles/murf-ai-falcon-2/) | Murf AI | 1 158 |
| 32 | [Gradium TTS (Aug 2026)](https://quelleia.com/voix/modeles/gradium-tts-aug-2026/) | Gradium | 1 153 |
| 32 | [MiniMax Speech 2.8 Turbo](https://quelleia.com/voix/modeles/minimax-speech-2-8-turbo/) | MiniMax | 1 153 |
| 34 | [Azure HD 2.5](https://quelleia.com/voix/modeles/microsoft-azure-hd-2-5/) | Microsoft | 1 145 |
| 35 | [Async Flash v1.5](https://quelleia.com/voix/modeles/async-flash-v1-5/) | Async | 1 140 |
| 36 | [Step TTS 2 (Mar 2026)](https://quelleia.com/voix/modeles/step-tts-2-mar-2026/) | StepFun | 1 138 |
| 37 | [Async Pro v1.0](https://quelleia.com/voix/modeles/async-pro-v1-0/) | Async | 1 129 |
| 38 | [MiniMax Speech 2.6 HD](https://quelleia.com/voix/modeles/minimax-speech-2-6-hd/) | MiniMax | 1 127 |
| 39 | [MiniMax Speech 2.6 Turbo](https://quelleia.com/voix/modeles/minimax-speech-2-6-turbo/) | MiniMax | 1 121 |
| 40 | [Simba 3.0](https://quelleia.com/voix/modeles/speechifyai-simba-3-0/) | SpeechifyAI | 1 117 |
| 41 | [Phonon 31M (English)](https://quelleia.com/voix/modeles/gradium-phonon-31m-english/) | Gradium | 1 114 |
| 42 | [Coda v2](https://quelleia.com/voix/modeles/rime-coda-v2/) | Rime | 1 112 |
| 43 | [Chatterbox HD](https://quelleia.com/voix/modeles/resemble-ai-chatterbox-hd/) | Resemble AI | 1 111 |
| 44 | [Fish Audio S2 Pro](https://quelleia.com/voix/modeles/fish-audio-s2-pro/) | Fish Audio | 1 108 |
| 45 | [TTS-1 HD](https://quelleia.com/voix/modeles/openai-tts-1-hd/) | OpenAI | 1 107 |
| 46 | [MiniMax Speech 02 HD](https://quelleia.com/voix/modeles/minimax-speech-02-hd/) | MiniMax | 1 105 |
| 47 | [Step Audio EditX (Mar 2026)](https://quelleia.com/voix/modeles/step-audio-editx-mar-2026/) | StepFun | 1 101 |
| 48 | [Eleven Multilingual v2](https://quelleia.com/voix/modeles/elevenlabs-multilingual-v2/) | ElevenLabs | 1 094 |
| 48 | [Eleven Turbo v2.5](https://quelleia.com/voix/modeles/elevenlabs-turbo-v2-5/) | ElevenLabs | 1 094 |
| 50 | [Speech 2.6](https://quelleia.com/voix/modeles/hithink-speech-2-6/) | HiThink | 1 093 |
| 51 | [Voxtral TTS](https://quelleia.com/voix/modeles/voxtral-tts/) | Mistral AI | 1 092 |
| 52 | [MiniMax Speech 02 Turbo](https://quelleia.com/voix/modeles/minimax-speech-02-turbo/) | MiniMax | 1 091 |
| 53 | [OpenAudio S1](https://quelleia.com/voix/modeles/openaudio-s1/) | Fish Audio | 1 087 |
| 54 | [TTS-1](https://quelleia.com/voix/modeles/openai-tts-1/) | OpenAI | 1 086 |
| 55 | [Gemini 2.5 Flash Lite TTS](https://quelleia.com/voix/modeles/google-gemini-2-5-flash-lite-tts/) | Google | 1 085 |
| 56 | [Eleven Flash v2.5](https://quelleia.com/voix/modeles/elevenlabs-flash-v2-5/) | ElevenLabs | 1 075 |
| 56 | [T2A-01-HD](https://quelleia.com/voix/modeles/minimax-t2a-01-hd/) | MiniMax | 1 075 |
| 58 | [GPT-Realtime-2](https://quelleia.com/voix/modeles/openai-gpt-realtime-2/) | OpenAI | 1 074 |
| 59 | [Studio](https://quelleia.com/voix/modeles/google-studio/) | Google | 1 073 |
| 60 | [Gemini 2.5 Flash TTS (Dec 2025)](https://quelleia.com/voix/modeles/google-gemini-2-5-flash-tts-dec-2025/) | Google | 1 071 |
| 60 | [Journey](https://quelleia.com/voix/modeles/google-journey/) | Google | 1 071 |
| 62 | [Kokoro 82M v1.0](https://quelleia.com/voix/modeles/kokoro-82m-v1-0/) | hexgrad | 1 064 |
| 62 | [Magpie-Multilingual 357M (Feb 2026)](https://quelleia.com/voix/modeles/nvidia-magpie-multilingual-357m-feb-2026/) | NVIDIA | 1 064 |
| 64 | [Polly Generative](https://quelleia.com/voix/modeles/amazon-polly-generative/) | Amazon | 1 063 |
| 65 | [Chirp 3: HD](https://quelleia.com/voix/modeles/google-chirp-3-hd/) | Google | 1 062 |
| 65 | [Maya 2 Flash](https://quelleia.com/voix/modeles/maya-2-flash/) | Maya Research | 1 062 |
| 67 | [Sonic 3](https://quelleia.com/voix/modeles/cartesia-sonic-3/) | Cartesia | 1 061 |
| 68 | [Octave 2](https://quelleia.com/voix/modeles/hume-ai-octave-2/) | Hume AI | 1 060 |
| 69 | [Coda](https://quelleia.com/voix/modeles/rime-coda/) | Rime | 1 053 |
| 69 | [Flux TTS](https://quelleia.com/voix/modeles/deepgram-flux-tts/) | Deepgram | 1 053 |
| 71 | [MiMo-V2.5-TTS](https://quelleia.com/voix/modeles/xiaomi-mimo-v2-5-tts/) | Xiaomi | 1 052 |
| 72 | [Async Flash v1.0](https://quelleia.com/voix/modeles/async-flash-v1-0/) | Async | 1 049 |
| 73 | [Maya 2 Global](https://quelleia.com/voix/modeles/maya-2-global/) | Maya Research | 1 048 |
| 74 | [Maya1](https://quelleia.com/voix/modeles/maya1/) | Maya Research | 1 047 |
| 75 | [OpenAudio S1 Mini](https://quelleia.com/voix/modeles/fish-audio-openaudio-s1-mini/) | Fish Audio | 1 043 |
| 76 | [Gemini 2.5 Pro (Dec 2025)](https://quelleia.com/voix/modeles/google-gemini-2-5-pro-dec-2025/) | Google | 1 040 |
| 76 | [Octave TTS](https://quelleia.com/voix/modeles/hume-ai-octave-tts/) | Hume AI | 1 040 |
| 78 | [Higgs TTS 3](https://quelleia.com/voix/modeles/boson-ai-higgs-tts-3-4b/) | Boson AI | 1 039 |
| 79 | [Bland Speech v3](https://quelleia.com/voix/modeles/bland-speech-v3/) | Bland AI | 1 036 |
| 80 | [Azure Neural](https://quelleia.com/voix/modeles/microsoft-azure-neural/) | Microsoft | 1 033 |
| 81 | [MAI-Voice-1](https://quelleia.com/voix/modeles/microsoft-mai-voice-1/) | Microsoft | 1 029 |
| 82 | [T2A-01-Turbo](https://quelleia.com/voix/modeles/minimax-t2a-01-turbo/) | MiniMax | 1 027 |
| 83 | [Polly Long-Form](https://quelleia.com/voix/modeles/amazon-polly-long-form/) | Amazon | 1 025 |
| 84 | [Lightning v3.1](https://quelleia.com/voix/modeles/smallest-ai-lightning-v3-1/) | Smallest AI | 1 024 |
| 85 | [Chatterbox](https://quelleia.com/voix/modeles/chatterbox/) | Resemble AI | 1 023 |
| 86 | [Raon SpeechLM](https://quelleia.com/voix/modeles/krafton-raon-speechlm/) | KRAFTON | 1 005 |
| 87 | [Zonos-v0.1](https://quelleia.com/voix/modeles/zyphra-zonos-v0-1/) | Zyphra | 1 000 |
| 88 | [Murf Speech Gen 2](https://quelleia.com/voix/modeles/murf-speech-gen-2/) | Murf AI | 986 |
| 89 | [OpenVoice v2](https://quelleia.com/voix/modeles/openvoice-v2/) | MyShell | 956 |
| 90 | [VibeVoice 1.5B](https://quelleia.com/voix/modeles/microsoft-vibevoice-1-5b/) | Microsoft | 953 |
| 91 | [Neuphonic TTS](https://quelleia.com/voix/modeles/neuphonic-tts/) | Neuphonic | 942 |
| 92 | [Qwen3 TTS Flash](https://quelleia.com/voix/modeles/alibaba-qwen3-tts-flash/) | Alibaba | 940 |
| 93 | [Qwen3 TTS](https://quelleia.com/voix/modeles/alibaba-qwen3-tts/) | Alibaba | 929 |
| 94 | [Kugel 3](https://quelleia.com/voix/modeles/kugel-3/) | KugelAudio | 925 |
| 95 | [WaveNet](https://quelleia.com/voix/modeles/google-wavenet/) | Google | 918 |
| 96 | [XTTS v2](https://quelleia.com/voix/modeles/coqui-xtts-v2/) | Coqui | 915 |
| 97 | [Mist V2](https://quelleia.com/voix/modeles/rime-mist-v2/) | Rime | 903 |
| 98 | [Polly Neural](https://quelleia.com/voix/modeles/amazon-polly-neural/) | Amazon | 895 |
| 99 | [Neural2](https://quelleia.com/voix/modeles/google-neural2/) | Google | 892 |
| 100 | [StyleTTS 2](https://quelleia.com/voix/modeles/styletts-2/) | Columbia University | 890 |
| 101 | [Standard](https://quelleia.com/voix/modeles/google-standard/) | Google | 886 |
| 102 | [Noiz TTS](https://quelleia.com/voix/modeles/noiz-tts/) | Noiz | 868 |
| 103 | [MetaVoice v1](https://quelleia.com/voix/modeles/metavoice-v1/) | MetaVoice | 848 |
| 104 | [Polly Standard](https://quelleia.com/voix/modeles/amazon-polly-standard/) | Amazon | 831 |

- Source : Artificial Analysis : https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (relevé du 9 novembre 2026)

Source : QUELLE IA, édition du 9 novembre 2026, quelleia.com, d'après Artificial Analysis.